Featured Image

Perspectives

Forecasts from models simply extrapolate the past into the future, and for stationary models the forecasts approach the model's estimates of the unconditional means of the variables. Survey expectations may be based on models, but are likely to adjust the model's forecasts to reflect knowledge the survey respondent might have about the future. How important does this knowledge tend to be? And how far ahead is it important? The paper addresses these questions by comparing the reported survey forecasts against forecasts which effectively assume the forecast moves monotonically to the endpoint or long-horizon forecast, as the forecast horizon increases. Departures from this path can be interpreted as useful knowledge about the future, to the extent that such departures enhance forecast accuracy.

Professor Michael P Clements
University of Reading

Read the Original

This page is a summary of: Are Professional Macroeconomic Forecasters Able To Do Better Than Forecasting Trends?, Journal of money credit and banking, March 2015, Wiley,
DOI: 10.1111/jmcb.12179.
You can read the full text:

Read

Contributors

The following have contributed to this page